{
  "fetched_at": "2026-10-19T23:13:36Z",
  "source_url": "https://www.kaggle.com/competitions/cudlfinance/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "This File contains dataset of daily prices of 505 stocks that currently compose the S&P 500 for the dates 01/01/2015 – 05/31/2018. Where each row corresponds to a trading day.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "\n<p>The motivation for this common task framework competition is to evaluate projects on time series prediction as part of the Deep Learning course on an equal footing.  The competition is optional for enrolled students in other projects. </p>\n\n<p><b>Goal: </b> Build an architecture which generates investment decisions across equities on a daily basis. </p>\n\n<p><b>Data: </b> Dataset of daily prices of 505 stocks that currently compose\nthe S&P 500 and CASH value for the dates 01/01/2015 – 05/31/2018.</p>\n\n\n<p> <b>Submission: </b> You are required to submit 505+1 entries of weights per day that should be allocated for investments in equities for next 30 days.</p>\n\n* Each weight entry stands for the % allocation of total purchase power for that\nday.\n\n* Interpretation of weight entry: if entry < 0 a stock is being sold short; if entry > 0\na stock is being bought; if entry = 0 a stock is excluded from the portfolio.\n\n* The extra entry is for 'CASH' – this adds another degree of freedom to your\ninvestment decision, and is equivalent to 'bias'.\n\n<b>Notes: </b>\n* You may choose a method for processing missing data and are allowed to augment the given dataset.\n\nEnjoy, and may the best team win.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "For every day in the test data, we have an ideal weight vector that optimizes the gains for that day. Every predicted vector (w_p) is scored with an RMSE loss w.r.t. the optimal weight vector.\n\nSubmission with a lower total loss will be placed higher on the leaderboard. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}